This project aims to investigates fundamental performance limits for machine learning algorithms, using techniques from information theory. For canonical tasks such as classification and high-dimensional estimation, the goal is to answer the question: "how fast can the accuracy of any algorithm improve as the number of available data samples grows?" The project will also explore the design of efficient algorithms that approach the optimal performance limits.
Applicants should have (or expect to obtain by the start date) at least a good 2.1 degree (and preferably a Masters degree) in Engineering, Applied Mathematics, Statistics or a related subject.
This studentship will cover all University fees and a maintenance allowance of at least £14.582 per year for UK students. EU students are eligible for a fees only award. Overseas students are not eligible and should not apply
Applicants may wish to contact Dr Venkataramanan (firstname.lastname@example.org) with a CV prior to applying
Applications should be submitted via the University of Cambridge Graduate Admissions web pages http://www.admin.cam.ac.uk/students/gradadmissions/prospec/apply/, with Dr Ramji Venkataramanan identified as the potential supervisor.
The University values diversity and is committed to equality of opportunity.